Scalable Property Valuation Models via Graph-based Deep Learning
This work addresses property valuation for real estate stakeholders with an incremental improvement over existing deep learning methods.
The paper tackled house price prediction by developing graph neural network models that capture spatial relationships, showing that transformer-based graph convolutions significantly improve accuracy on a dataset of 200,000 houses in Santiago, Chile.
This paper aims to enrich the capabilities of existing deep learning-based automated valuation models through an efficient graph representation of peer dependencies, thus capturing intricate spatial relationships. In particular, we develop two novel graph neural network models that effectively identify sequences of neighboring houses with similar features, employing different message passing algorithms. The first strategy consider standard spatial graph convolutions, while the second one utilizes transformer graph convolutions. This approach confers scalability to the modeling process. The experimental evaluation is conducted using a proprietary dataset comprising approximately 200,000 houses located in Santiago, Chile. We show that employing tailored graph neural networks significantly improves the accuracy of house price prediction, especially when utilizing transformer convolutional message passing layers.